How to use from the
Use from the
MLX library
# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir MLXCreator-ACEStep-1.5-4bit MLXCreator/MLXCreator-ACEStep-1.5-4bit

MLX Creator โ€” ACE-Step 1.5 (4-bit)

MLX-format weights for MLX Creator (https://github.com/rynky2436/MLX-Creator) โ€” local generative media on Apple Silicon.

Based on: mlx-community/ACE-Step1.5-MLX

This is an MLX repackaging/conversion; the original credit above is retained per its license.

Downloads last month
6
Safetensors
Model size
0.6B params
Tensor type
F32
ยท
U32
ยท
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support